Diffusion-Weighted Imaging for Skin Pathologies of the Breast-A Feasibility Study.

Several breast pathologies can affect the skin, and clinical pathways might differ significantly depending on the underlying diagnosis. This study investigates the feasibility of using diffusion-weighted imaging (DWI) to differentiate skin pathologies in breast MRIs. This retrospective study included 88 female patients who underwent diagnostic breast MRI (1.5 or 3T), including DWI. Skin areas were manually segmented, and the apparent diffusion coefficients (ADCs) were compared between different pathologies: inflammatory breast cancer (IBC; n = 5), benign skin inflammation (BSI; n = 11), Paget's disease (PD; n = 3), and skin-involved breast cancer (SIBC; n = 11). Fifty-eight women had healthy skin (H; n = 58). The SIBC group had a significantly lower mean ADC than the BSI and IBC groups. These differences persisted for the first-order features of the ADC (mean, median, maximum, and minimum) only between the SIBC and BSI groups. The mean ADC did not differ significantly between the BSI and IBC groups. Quantitative DWI assessments demonstrated differences between various skin-affecting pathologies, but did not distinguish clearly between all of them. More extensive studies are needed to assess the utility of quantitative DWI in supplementing the diagnostic assessment of skin pathologies in breast imaging.

Lesion-conditioning of synthetic MRI-derived subtraction-MIPs of the breast using a latent diffusion model.

The purpose of this feasibility study is to investigate if latent diffusion models (LDMs) are capable to generate contrast enhanced (CE) MRI-derived subtraction maximum intensity projections (MIPs) of the breast, which are conditioned by lesions. We trained an LDM with n = 2832 CE-MIPs of breast MRI examinations of n = 1966 patients (median age: 50 years) acquired between the years 2015 and 2020. The LDM was subsequently conditioned with n = 756 segmented lesions from n = 407 examinations, indicating their location and BI-RADS scores. By applying the LDM, synthetic images were generated from the segmentations of an independent validation dataset. Lesions, anatomical correctness, and realistic impression of synthetic and real MIP images were further assessed in a multi-rater study with five independent raters, each evaluating n = 204 MIPs (50% real/50% synthetic images). The detection of synthetic MIPs by the raters was akin to random guessing with an AUC of 0.58. Interrater reliability of the lesion assessment was high both for real (Kendall's W = 0.77) and synthetic images (W = 0.85). A higher AUC was observed for the detection of suspicious lesions (BI-RADS ≥ 4) in synthetic MIPs (0.88 vs. 0.77; p = 0.051). Our results show that LDMs can generate lesion-conditioned MRI-derived CE subtraction MIPs of the breast, however, they also indicate that the LDM tended to generate rather typical or 'textbook representations' of lesions.

Initial experience with a next-generation low-field MRI scanner: Potential for breast imaging?

PURPOSE: Broader clinical adoption of breast magnetic resonance imaging (MRI) faces challenges such as limited availability and high procedural costs. Low-field technology has shown promise in addressing these challenges. We report our initial experience using a next-generation scanner for low-field breast MRI at 0.55T. METHODS: This initial cases series was part of an institutional review board-approved prospective study using a 0.55T scanner (MAGNETOM Free.Max, Siemens Healthcare, Erlangen/Germany: height < 2 m, weight < 3.2 tons, no quench pipe) equipped with a seven-channel breast coil (Noras, Höchberg/Germany). A multiparametric breast MRI protocol consisting of dynamic T1-weighted, T2-weighted, and diffusion-weighted sequences was optimized for 0.55T. Two radiologists with 12 and 20 years of experience in breast MRI evaluated the examinations. RESULTS: Twelve participants (mean age: 55.3 years, range: 36-78 years) were examined. The image quality was diagnostic in all examinations and not impaired by relevant artifacts. Typical imaging phenotypes were visualized. The scan time for a complete, non-abbreviated breast MRI protocol ranged from 10:30 to 18:40 min. CONCLUSION: This initial case series suggests that low-field breast MRI is feasible at diagnostic image quality within an acceptable examination time.

Smart forecasting of artifacts in contrast-enhanced breast MRI before contrast agent administration.

OBJECTIVES: To evaluate whether artifacts on contrast-enhanced (CE) breast MRI maximum intensity projections (MIPs) might already be forecast before gadolinium-based contrast agent (GBCA) administration during an ongoing examination by analyzing the unenhanced T1-weighted images acquired before the GBCA injection. MATERIALS AND METHODS: This IRB-approved retrospective analysis consisted of n = 2884 breast CE MRI examinations after intravenous administration of GBCA, acquired with n = 4 different MRI devices at different field strengths (1.5 T/3 T) during clinical routine. CE-derived subtraction MIPs were used to conduct a multi-class multi-reader evaluation of the presence and severity of artifacts with three independent readers. An ensemble classifier (EC) of five DenseNet models was used to predict artifacts for the post-contrast subtraction MIPs, giving as the input source only the pre-contrast T1-weighted sequence. Thus, the acquisition directly preceded the GBCA injection. The area under ROC (AuROC) and diagnostics accuracy scores were used to assess the performance of the neural network in an independent holdout test set (n = 285). RESULTS: After majority voting, potentially significant artifacts were detected in 53.6% (n = 1521) of all breast MRI examinations (age 49.6 ± 12.6 years). In the holdout test set (mean age 49.7 ± 11.8 years), at a specificity level of 89%, the EC could forecast around one-third of artifacts (sensitivity 31%) before GBCA administration, with an AuROC = 0.66. CONCLUSION: This study demonstrates the capability of a neural network to forecast the occurrence of artifacts on CE subtraction data before the GBCA administration. If confirmed in larger studies, this might enable a workflow-blended approach to prevent breast MRI artifacts by implementing in-scan personalized predictive algorithms. CLINICAL RELEVANCE STATEMENT: Some artifacts in contrast-enhanced breast MRI maximum intensity projections might be predictable before gadolinium-based contrast agent injection using a neural network. KEY POINTS: • Potentially significant artifacts can be observed in a relevant proportion of breast MRI subtraction sequences after gadolinium-based contrast agent administration (GBCA). • Forecasting the occurrence of such artifacts in subtraction maximum intensity projections before GBCA administration for individual patients was feasible at 89% specificity, which allowed correctly predicting one in three future artifacts. • Further research is necessary to investigate the clinical value of such smart personalized imaging approaches.

Impact of velocity- and acceleration-compensated encodings on signal dropout and black-blood state in diffusion-weighted magnetic resonance liver imaging at clinical TEs.

PURPOSE: The study aims to develop easy-to-implement concomitant field-compensated gradient waveforms with varying velocity-weighting (M1) and acceleration-weighting (M2) levels and to evaluate their efficacy in correcting signal dropouts and preserving the black-blood state in liver diffusion-weighted imaging. Additionally, we seek to determine an optimal degree of compensation that minimizes signal dropouts while maintaining blood signal suppression. METHODS: Numerically optimized gradient waveforms were adapted using a novel method that allows for the simultaneous tuning of M1- and M2-weighting by changing only one timing variable. Seven healthy volunteers underwent diffusion-weighted magnetic resonance imaging (DWI) with five diffusion encoding schemes (monopolar, velocity-compensated (M1 = 0), acceleration-compensated (M1 = M2 = 0), 84%-M1-M2-compensated, 67%-M1-M2-compensated) at b-values of 50 and 800 s/mm2 at a constant echo time of 70 ms. Signal dropout correction and apparent diffusion coefficients (ADCs) were quantified using regions of interest in the left and right liver lobe. The blood appearance was evaluated using two five-point Likert scales. RESULTS: Signal dropout was more pronounced in the left lobe (19%-42% less signal than in the right lobe with monopolar scheme) and best corrected by acceleration-compensation (8%-10% less signal than in the right lobe). The black-blood state was best with monopolar encodings and decreased significantly (p < 0.001) with velocity- and/or acceleration-compensation. The partially M1-M2-compensated encoding schemes could restore the black-blood state again. Strongest ADC bias occurred for monopolar encodings (difference between left/right lobe of 0.41 µm2/ms for monopolar vs. < 0.12 µm2/ms for the other encodings). CONCLUSION: All of the diffusion encodings used in this study demonstrated suitability for routine DWI application. The results indicate that a perfect value for the level of M1-M2-compensation does not exist. However, among the examined encodings, the 84%-M1-M2-compensated encodings provided a suitable tradeoff.

Prevalence and influencing factors for artifact development in breast MRI-derived maximum intensity projections.

BACKGROUND: Magnetic resonance imaging (MRI) provides high diagnostic sensitivity for breast cancer. However, MRI artifacts may impede the diagnostic assessment. This is particularly important when evaluating maximum intensity projections (MIPs), such as in abbreviated MRI (AB-MRI) protocols, because high image quality is desired as a result of fewer sequences being available to compensate for problems. PURPOSE: To describe the prevalence of artifacts on dynamic contrast enhanced (DCE) MRI-derived MIPs and to investigate potentially associated attributes. MATERIAL AND METHODS: For this institutional review board approved retrospective analysis, MIPs were generated from subtraction series and cropped to represent the left and right breasts as regions of interest. These images were labeled by three independent raters regarding the presence of MRI artifacts. MRI artifact prevalence and associations with patient characteristics and technical attributes were analyzed using descriptive statistics and generalized linear models (GLMMs). RESULTS: The study included 2524 examinations from 1794 patients (median age 50 years), performed on 1.5 and 3.0 Tesla MRI systems. Overall inter-rater agreement was kappa = 0.54. Prevalence of significant unilateral artifacts was 29.2% (736/2524), whereas bilateral artifacts were present in 37.8% (953/2524) of all examinations. According to the GLMM, artifacts were significantly positive associated with age (odds ratio [OR] = 1.52) and magnetic field strength (OR = 1.55), whereas a negative effect could be shown for body mass index (OR = 0.95). CONCLUSION: MRI artifacts on DCE subtraction MIPs of the breast, as used in AB-MRI, are a relevant topic. Our results show that, besides the magnetic field strength, further associated attributes are patient age and body mass index, which can provide possible targets for artifact reduction.

Feature-guided deep learning reduces signal loss and increases lesion CNR in diffusion-weighted imaging of the liver.

PURPOSE: This research aims to develop a feature-guided deep learning approach and compare it with an optimized conventional post-processing algorithm in order to enhance the image quality of diffusion-weighted liver images and, in particular, to reduce the pulsation-induced signal loss occurring predominantly in the left liver lobe. METHODS: Data from 40 patients with liver lesions were used. For the conventional approach, the best-suited out of five examined algorithms was chosen. For the deep learning approach, a U-Net was trained. Instead of learning "gold-standard" target images, the network was trained to optimize four image features (lesion CNR, vessel darkness, data consistency, and pulsation artifact reduction), which could be assessed quantitatively using manually drawn ROIs. A quality score was calculated from these four features. As an additional quality assessment, three radiologists rated different features of the resulting images. RESULTS: The conventional approach could substantially increase the lesion CNR and reduce the pulsation-induced signal loss. However, the vessel darkness was reduced. The deep learning approach increased the lesion CNR and reduced the signal loss to a slightly lower extent, but it could additionally increase the vessel darkness. According to the image quality score, the quality of the deep-learning images was higher than that of the images obtained using the conventional approach. The radiologist ratings were mostly consistent with the quantitative scores, but the overall quality ratings differed among the readers. CONCLUSION: Unlike the conventional algorithm, the deep-learning algorithm increased the vessel darkness. Therefore, it may be a viable alternative to conventional algorithms.

Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI.

The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/mm2 was acquired. From these, 2D MIP images were computed and the left and right breast were cropped out as regions of interest (ROI). The presence of MRI image artifacts on the ROIs was rated by three independent observers. Artifact prevalence in the dataset was 37% (961 out of 2618 images). A DenseNet was trained with a fivefold cross-validation to identify artifacts on these images. In an independent holdout test dataset (n = 350 images) artifacts were detected by the neural network with an area under the precision-recall curve of 0.921 and a positive predictive value of 0.981. Our results show that a deep learning algorithm is capable to identify MRI artifacts in breast DWI-derived MIPs, which could help to improve quality assurance approaches for DWI sequences of breast examinations in the future.

Effects of High-Intensity Resistance Training on Visceral Adipose Tissue and Abdominal Aortic Calcifications in Older Men with Osteosarcopenia - Results from the FrOST Study.

Purpose: To evaluate the effect of a high-intensity resistance training (HIT-RT) on visceral adipose tissue (VAT) and abdominal aortic calcifications (AAC). Patients and Methods: We conducted a post hoc analysis of the Franconian Osteopenia and Sarcopenia Trial (FrOST). 43 community-dwelling men with osteosarcopenia aged 72 years and older were randomly allocated to a supervised high-intensity resistance training (HIT-RT) twice weekly for 18 months (EG; n=21) and a non-training control group (CG; n=22). Non-contrast enhanced 2-point Dixon MRI scans covering mid L2 to mid L3 were acquired to measure VAT volume inside the abdominal cavity. Volume of AAC and hard plaques in renal arteries, truncus celiacus and superior mesenteric artery was measured by computed tomography (CT) scans covering mid T12 to mid L3. Intention-to-treat analysis with imputation for missing data was used to determine longitudinal changes in VAT and AAC volume. Correlations were used to determine associations between VAT and AAC. Results: Significant reduction of VAT volume in the EG (-7.7%; p<0.001) combined with no change in the CG (-1.3%; p=0.46) resulted in a significant 6.4% between group effect (p=0.022). We observed a significant increase of AAC volume in EG (+10.3%; p<0.001) and CG (12.0%; p<0.001). AAC differences between groups were not significant (p=0.57). In vascular outlets increases in volume of the hard plaques were observed in both groups, however, not all of them were significant. There was no significant correlation between changes in VAT and AAC volumes. Conclusion: The study confirmed a positive impact of HIT-RT on the metabolic and cardiovascular risk profile with respect to reduction of VAT volume. No positive exercise effect on AAC was observed. However, there was a further progression of AAC volume independent of group affiliation. Whether different exercise regimen may show a positive effect on AAC remains subject to further studies.

Sodium and quantitative hydrogen parameter changes in muscle tissue after eccentric exercise and in delayed-onset muscle soreness assessed with magnetic resonance imaging.

The objective of the current study was to assess sodium (23 Na) and quantitative proton (1 H) parameter changes in muscle tissue with magnetic resonance imaging (MRI) after eccentric exercise and in delayed-onset muscle soreness (DOMS). Fourteen participants (mean age: 25 ± 4 years) underwent 23 Na/1 H MRI of the calf muscle on a 3-T MRI system before exercise (t0), directly after eccentric exercise (t1), and 48 h postintervention (t2). In addition to tissue sodium concentration (TSC), intracellular-weighted sodium (ICwS) signal was acquired using a three-dimensional density-adapted radial projection readout with an additional inversion recovery preparation module. Phantoms containing saline solution served as references to quantify sodium concentrations. The 1 H MRI protocol consisted of a T1 -weighted turbo spin echo sequence, a T2 -weighted turbo inversion recovery, as well as water T2 mapping and water T1 mapping. Additionally, blood serum creatine kinase (CK) levels were assessed at baseline and 48 h after exercise. The TSC and ICwS of exercised muscles increased significantly from t0 to t1 and decreased significantly from t1 to t2. In the soleus muscle (SM), ICwS decreased below baseline values at t2. In the tibialis anterior muscle (TA), TSC and ICwS remained at baseline levels at each measurement point. However, high-CK participants (i.e., participants with a more than 10-fold CK increase, n = 3) displayed different behavior, with 2- to 4-fold increases in TSC values in the medial gastrocnemius muscle (MGM) at t2. 1 H water T1 relaxation times increased significantly after 48 h in the MGM and SM. 1 H water T2 relaxation times and muscle volume increased in the MGM at t2. Sodium MRI parameters and water relaxation times peaked at different points. Whereas water relaxation times were highest at t2, sodium MRI parameters had already returned to baseline values (or even below baseline values, for low-CK participants) by this point. The observed changes in ion concentrations and water relaxation time parameters could enable a better understanding of the physiological processes during DOMS and muscle regeneration. In the future, this might help to optimize training and to reduce associated sports injuries.

Pulmonary Dysfunction after Pediatric COVID-19.

Background Long COVID occurs at a lower frequency in children and adolescents than in adults. Morphologic and free-breathing phase-resolved functional low-field-strength MRI may help identify persistent pulmonary manifestations after SARS-CoV-2 infection. Purpose To characterize both morphologic and functional changes of lung parenchyma at low-field-strength MRI in children and adolescents with post-COVID-19 condition compared with healthy controls. Materials and Methods Between August and December 2021, a cross-sectional clinical trial using low-field-strength MRI was performed in children and adolescents from a single academic medical center. The primary outcome was the frequency of morphologic changes at MRI. Secondary outcomes included MRI-derived functional proton ventilation and perfusion parameters. Clinical symptoms, the duration from positive reverse transcriptase-polymerase chain reaction test result, and serologic parameters were compared with imaging results. Nonparametric tests for pairwise and corrected tests for groupwise comparisons were applied to assess differences in healthy controls, recovered participants, and those with long COVID. Results A total of 54 participants after COVID-19 infection (mean age, 11 years ± 3 [SD]; 30 boys [56%]) and nine healthy controls (mean age, 10 years ± 3; seven boys [78%]) were included: 29 (54%) in the COVID-19 group had recovered from infection and 25 (46%) were classified as having long COVID on the day of enrollment. Morphologic abnormality was identified in one recovered participant. Both ventilated and perfused lung parenchyma (ventilation-perfusion [V/Q] match) was higher in healthy controls (81% ± 6.1) compared with the recovered group (62% ± 19; P = .006) and the group with long COVID (60% ± 20; P = .003). V/Q match was lower in patients with time from COVID-19 infection to study participation of less than 180 days (63% ± 20; P = .03), 180-360 days (63% ± 18; P = .03), and 360 days (41% ± 12; P < .001) as compared with the never-infected healthy controls (81% ± 6.1). Conclusion Low-field-strength MRI showed persistent pulmonary dysfunction in children and adolescents who recovered from COVID-19 and those with long COVID. Clinical trial registration no. NCT04990531 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Paltiel in this issue.

[Li-Fraumeni syndrome]. / Li-Fraumeni-Syndrom.

BACKGROUND: The autosomal dominant inherited Li-Fraumeni syndrome (LFS) increases the lifetime risk of developing a malignancy to almost 100%. Although breast cancer, central nervous system (CNS) tumors and sarcomas are particularly common, tumors can ultimately occur almost anywhere in the body. As causal therapy is not available, the primary focus for improving the prognosis is early cancer detection. To this end, current cancer surveillance recommendations include a series of examinations including regular imaging beginning at birth. CHALLENGES IN IMAGING IN LFS: Due to the wide range of tumor entities that can occur in individuals affected by LFS, a sensitive detection requires imaging of various tissue contrasts; however, because life-long screening is potentially initiated at a young age, this requirement for comprehensiveness must be balanced against the presumed high psychological burden associated with frequent or invasive examinations. As radiation exposure may lead to an increased (secondary) tumor risk, computed tomography (CT) and X­ray examinations should be avoided as far as possible. CURRENT STATUS AND PERSPECTIVES: Because annual whole-body magnetic resonance imaging (MRI) has no radiation exposure and yet a high sensitivity for many tumors, it forms the basis of the recommended imaging; however, due to the rarity of the syndrome, expertise is sometimes lacking and whole-body MRI examinations are performed heterogeneously and sometimes with limited diagnostic quality. Optimization and standardization of MRI protocols should therefore be pursued. In addition, the need for an intravenously administered contrast agent has not been conclusively clarified despite its high relevance.

Assessing the influence of the menstrual cycle on APT CEST-MRI in the human breast.

PURPOSE: In fibroglandular breast tissue, conventional dynamic contrast-enhanced MR-mammography is known to be affected by water content changes during the menstrual cycle. Likewise, amide proton transfer (APT) chemical exchange saturation transfer (CEST)-MRI might be inherently prone to the menstrual cycle, as CEST signals are indirectly detected via the water signal. The purpose of this study was to investigate the influence of the menstrual cycle on APT CEST-MRI in fibroglandular breast tissue. METHOD: Ten healthy premenopausal women (19-34 years) were included in this IRB approved prospective study and examined twice during their menstrual cycle. Examination one and two were performed during the first half (day 2-8) and the second half (day 15-21) of the menstrual cycle, respectively. As a reference for the APT signal in malignant breast tumor tissue, previously reported data of nine breast cancer patients were included in this study. CEST-MRI (B1 = 0.7µT) was performed on a 7 T whole-body scanner followed by a multi-Lorentzian fit analysis. The APT signal was corrected for B0/B1-field inhomogeneities, fat signal contribution, and relaxation effects of the water signal and evaluated in the fibroglandular breast tissue. Intra-individual APT signal differences between examination one and two were compared using the Wilcoxon signed-rank test. The level of significance was set at p < 0.05. RESULTS: The APT signal showed no significant difference in the fibroglandular breast tissue of healthy premenopausal volunteers throughout the menstrual cycle (p = 1.00) (examination 1 vs. examination 2: mean and standard deviation = 3.24 ± 0.68%Hz vs. 3.30 ± 0.73%Hz, median and IQR = 3.36%Hz and 0.87%Hz vs. 3.38%Hz and 0.71%Hz). CONCLUSION: The present study provides an important basis for the clinical application of APT CEST-MRI as an additional contrast mechanism in MR-mammography, as menstrual cycle-related APT signal fluctuations seem to be negligible compared to the APT signal increase in breast cancer tissue.

Free-Breathing Low-Field MRI of the Lungs Detects Functional Alterations Associated With Persistent Symptoms After COVID-19 Infection.

OBJECTIVES: With the COVID-19 pandemic, repetitive lung examinations have become necessary to follow-up symptoms and associated alterations. Low-field MRI, benefiting from reduced susceptibility effects, is a promising alternative for lung imaging to limit radiations absorbed by patients during CT examinations, which also have limited capability to assess functional alterations. The aim of this investigative study was to explore the functional abnormalities that free-breathing 0.55 T MRI in combination with the phase-resolved functional lung (PREFUL) analysis could identify in patients with persistent symptoms after COVID-19 infection. MATERIALS AND METHODS: Seventy-four COVID-19 patients and 8 healthy volunteers were prospectively scanned in free-breathing with a balanced steady-state free-precession sequence optimized at 0.55 T, 5 months postinfection on average. Normalized perfusion (Q), fractional ventilation (FV), and flow-volume loop correlation (FVLc) maps were extracted with the PREFUL technique. Q, FV, and FVLc defects as well as defect overlaps between these metrics were quantified. Morphological turbo-spin-echo images were also acquired, and the extent of abnormalities was scored by a board-certified radiologist. To investigate the functional correlates of persistent symptoms, a recursive feature elimination algorithm was applied to find the most informative variables to detect the presence of persistent symptoms with a logistic regression model and a cross-validation strategy. All MRI metrics, sex, age, body mass index, and the presence of preexisting lung conditions were included. RESULTS: The most informative variables to detect persistent symptoms were the percentage of concurrent Q and FVLc defects and of areas free of those defects. A detection accuracy of 71.4% was obtained with these 2 variables when fitting the model on the entire dataset. Although none of the single variables differed between patients with and without persistent symptoms ( P > 0.05), the combined score of these 2 variables did ( P < 0.02). This score also showed a consistent increase from healthy volunteers (7.7) to patients without persistent symptoms (8.2) and with persistent symptoms (8.6). The morphological abnormality score showed poor correlation with the functional parameters. CONCLUSIONS: Functional pulmonary examinations using free-breathing 0.55 T MRI with PREFUL analysis revealed potential quantitative markers of impaired lung function in patients with persistent symptoms after COVID-19 infection, potentially complementing morphologic imaging. Future work is needed to explore the translational relevance and clinical implication of these findings.

Flow-compensated diffusion encoding in MRI for improved liver metastasis detection.

Magnetic resonance (MR) diffusion-weighted imaging (DWI) is often used to detect focal liver lesions (FLLs), though DWI image quality can be limited in the left liver lobe owing to the pulsatile motion of the nearby heart. Flow-compensated (FloCo) diffusion encoding has been shown to reduce this pulsation artifact. The purpose of this prospective study was to intra-individually compare DWI of the liver acquired with conventional monopolar and FloCo diffusion encoding for assessing metastatic FLLs in non-cirrhotic patients. Forty patients with known or suspected multiple metastatic FLLs were included and measured at 1.5 T field strength with a conventional (monopolar) and a FloCo diffusion encoding EPI sequence (single refocused; b-values, 50 and 800 s/mm2). Two board-certified radiologists analyzed the DWI images independently. They issued Likert-scale ratings (1 = worst, 5 = best) for pulsation artifact severity and counted the difference of lesions visible at b = 800 s/mm² separately for small and large FLLs (i.e., < 1 cm or > 1 cm) and separately for left and right liver lobe. Differences between the two diffusion encodings were assessed with the Wilcoxon signed-rank test. Both readers found a reduction in pulsation artifact in the liver with FloCo encoding (p < 0.001 for both liver lobes). More small lesions were detected with FloCo diffusion encoding in both liver lobes (left lobe: six and seven additional lesions by readers 1 and 2, respectively; right lobe: five and seven additional lesions for readers 1 and 2, respectively). Both readers found one additional large lesion in the left liver lobe. Thus, flow-compensated diffusion encoding appears more effective than monopolar diffusion encoding for the detection of liver metastases.

Automated artifact detection in abbreviated dynamic contrast-enhanced (DCE) MRI-derived maximum intensity projections (MIPs) of the breast.

OBJECTIVES: To automatically detect MRI artifacts on dynamic contrast-enhanced (DCE) maximum intensity projections (MIPs) of the breast using deep learning. METHODS: Women who underwent clinically indicated breast MRI between October 2015 and December 2019 were included in this IRB-approved retrospective study. We employed two convolutional neural network architectures (ResNet and DenseNet) to detect the presence of artifacts on DCE MIPs of the left and right breasts. Networks were trained on images acquired up to and including the year 2018 using a 5-fold cross-validation (CV). Ensemble classifiers were built with the resulting CV models and applied to an independent holdout test dataset, which was formed by images acquired in 2019. RESULTS: Our study sample contained 2265 examinations from 1794 patients (median age at first acquisition: 50 years [IQR: 17 years]), corresponding to 1827 examinations of 1378 individuals in the training dataset and 438 examinations of 416 individuals in the holdout test dataset with a prevalence of image-level artifacts of 53% (1951/3654 images) and 43% (381/876 images), respectively. On the holdout test dataset, the ResNet and DenseNet ensembles demonstrated an area under the ROC curve of 0.92 and 0.94, respectively. CONCLUSION: Neural networks are able to reliably detect artifacts that may impede the diagnostic assessment of MIPs derived from DCE subtraction series in breast MRI. Future studies need to further explore the potential of such neural networks to complement quality assurance and improve the application of DCE MIPs in a clinical setting, such as abbreviated protocols. KEY POINTS: • Deep learning classifiers are able to reliably detect MRI artifacts in dynamic contrast-enhanced protocol-derived maximum intensity projections of the breast. • Automated quality assurance of maximum intensity projections of the breast may be of special relevance for abbreviated breast MRI, e.g., in high-throughput settings, such as cancer screening programs.

[Imaging of the lung using low-field magnetic resonance imaging]. / Lungenbildgebung in der Niederfeld-Magnetresonanztomographie.

BACKGROUND: Lung magnetic resonance imaging (MRI) examinations are challenging and have not become established in the routine clinical setting. Recent developments in low-field MRI, combined with computer-assisted algorithms for acquisition and evaluation, promise new perspectives for imaging of pulmonary diseases. OBJECTIVES: This review aims to inform about the physical advantages of low-field MRI for imaging the lungs, provide a review of the sparse literature, and present first results from a new low-field MRI scanner. MATERIALS AND METHODS: This article provides information on the physical principles, an review of the literature, and our first experiences in lung imaging on a modern 0.55 T MRI. CONCLUSION: Low-field MRI (< 1 T) may have technical and economic advantages over higher field strength MRI in lung imaging. The physical preconditions of low-field MRI are advantageous for imaging the lungs due to reduced susceptibility effects, increased transversal relaxation times, and lower specific absorption rates. The lower investment and operating costs may enable increased availability and sustainability. Combining modern sequences and computer-based image processing may expand beyond morphological imaging by providing spatially and temporally resolved functional examinations of the lung parenchyma without ionizing radiation. In critical scenarios, like screening and short-term follow-up examinations, and patients at risk, low-field MRI may bridge the gap. These indications may include acute and chronic pulmonary diseases in pediatric patients and suspected pulmonary embolisms in pregnant women.

Advanced neural networks for classification of MRI in psoriatic arthritis, seronegative, and seropositive rheumatoid arthritis.

OBJECTIVES: To evaluate whether neural networks can distinguish between seropositive RA, seronegative RA, and PsA based on inflammatory patterns from hand MRIs and to test how psoriasis patients with subclinical inflammation fit into such patterns. METHODS: ResNet neural networks were utilized to compare seropositive RA vs PsA, seronegative RA vs PsA, and seropositive vs seronegative RA with respect to hand MRI data. Results from T1 coronal, T2 coronal, T1 coronal and axial fat-suppressed contrast-enhanced (CE), and T2 fat-suppressed axial sequences were used. The performance of such trained networks was analysed by the area under the receiver operating characteristics curve (AUROC) with and without presentation of demographic and clinical parameters. Additionally, the trained networks were applied to psoriasis patients without clinical arthritis. RESULTS: MRI scans from 649 patients (135 seronegative RA, 190 seropositive RA, 177 PsA, 147 psoriasis) were fed into ResNet neural networks. The AUROC was 75% for seropositive RA vs PsA, 74% for seronegative RA vs PsA, and 67% for seropositive vs seronegative RA. All MRI sequences were relevant for classification, however, when deleting contrast agent-based sequences the loss of performance was only marginal. The addition of demographic and clinical data to the networks did not provide significant improvements for classification. Psoriasis patients were mostly assigned to PsA by the neural networks, suggesting that a PsA-like MRI pattern may be present early in the course of psoriatic disease. CONCLUSION: Neural networks can be successfully trained to distinguish MRI inflammation related to seropositive RA, seronegative RA, and PsA.

Differentiating Benign and Malignant Breast Lesions in Diffusion Kurtosis MRI: Does the Averaging Procedure Matter?

BACKGROUND: Diffusion kurtosis imaging (DKI) is used to differentiate between benign and malignant breast lesions. DKI fits are performed either on voxel-by-voxel basis or using volume-averaged signal. PURPOSE: Investigate and compare DKI parameters' diagnostic performance using voxel-by-voxel and volume-averaged signal fit approach. STUDY TYPE: Retrospective. STUDY POPULATION: A total of 104 patients, aged 24.1-86.4 years. FIELD STRENGTH/SEQUENCE: A 3 T Spin-echo planar diffusion-weighted sequence with b-values: 50 s/mm2 , 750 s/mm2 , and 1500 s/mm2 . Dynamic contrast enhanced (DCE) sequence. ASSESSMENT: Lesions were manually segmented by M.P. under supervision of S.O. (2 and 5 years of experience in breast MRI). DKI fits were performed on voxel-by-voxel basis and with volume-averaged signal. Diagnostic performance of DKI parameters D K (kurtosis corrected diffusion coefficient) and kurtosis K was compared between both approaches. STATISTICAL TESTS: Receiver operating characteristics analysis and area under the curve (AUC) values were computed. Wilcoxon rank sum and Students t-test tested DKI parameters for significant (P <0.05) difference between benign and malignant lesions. DeLong test was used to test the DKI parameter performance for significant fit approach dependency. Correlation between parameters of the two approaches was determined by Pearson correlation coefficient. RESULTS: DKI parameters were significantly different between benign and malignant lesions for both fit approaches. Median benign vs. malignant values for voxel-by-voxel and volume-averaged approach were 2.00 vs. 1.28 ( D K in µm2 /msec), 2.03 vs. 1.26 ( D K in µm2 /msec), 0.54 vs. 0.90 ( K ), 0.55 vs. 0.99 ( K ). AUC for voxel-by-voxel and volume-averaged fit were 0.9494 and 0.9508 ( D K ); 0.9175 and 0.9298 ( K ). For both, AUC did not differ significantly (P = 0.20). Correlation of values between the two approaches was very high (r = 0.99 for D K and r = 0.97 for K ). DATA CONCLUSION: Voxel-by-voxel and volume-averaged signal fit approach are equally well suited for differentiating between benign and malignant breast lesions in DKI. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

Pancreatic imaging using diffusivity mapping - Influence of sequence technique on qualitative and quantitative analysis.

PURPOSE: To compare image quality of an optimized diffusion weighted imaging (DWI) sequence with advanced post-processing and motion correction (advanced-EPI) to a standard DWI protocol (standard-EPI) in pancreatic imaging. MATERIALS AND METHODS: 62 consecutive patients underwent abdominal MRI at 1.5 T were included in this retrospective analysis of data collected as part of an IRB approved study. All patients received a standard-EPI and an advanced-EPI DWI with advanced post-processing and motion correction. Two blinded radiologists evaluated the parameters image quality, detail of parenchyma, sharpness of boundaries and discernibility from adjacent structures on b = 900 s/mm2 images using a Likert-like scale. Segmentation of pancreatic head, body and tail were obtained and apparent diffusion coefficient (ADC) was calculated separately for each region. Apparent tissue-to-background ratio (TBR) was calculated at b = 50 s/mm2 and at b = 900 s/mm2. RESULTS: The advanced-EPI yielded significantly higher scores for pancreatic parameters of image quality, detail level of parenchyma, sharpness of boundaries and discernibility from adjacent structures in comparison to standard-EPI (p < 0.001 for all, kappa = [0.46,0.71]) and was preferred in 96% of the cases when directly compared. ADC of the pancreas was 7% lower in advanced-EPI (1.236 ± 0.152 vs. 1.146 ± 0.126 µm2/ms, p < 0.001). ADC in the pancreatic tail was significantly lower for both sequences compared to head and body (all p < 0.001). There was comparable TBR for both sequences at b = 50 s/mm2 (standard-EPI: 19.0 ± 5.9 vs. advanced-EPI: 19.0 ± 6.4, p = 0.96), whereas at b = 900 s/mm2, TBR was 51% higher for advanced-EPI (standard-EPI: 7.1 ± 2.5 vs. advanced-EPI: 10.8 ± 5.1, p < 0.001). CONCLUSION: An advanced DWI sequence might increase image quality for focused imaging of the pancreas and providing improved parenchymal detail levels compared to a standard DWI.